• Sehan Park, Jeoung Kun Kim, Min Cheol Chang, Jeong Jin Park, Jae Jun Yang, and Gun Woo Lee.
• Department of Orthopedic Surgery, Dongguk University Ilsan Hospital, Goyang-si, Gyeonggi-do Province, Republic of Korea.
• Spine. 2022 Dec 1; 47 (23): 164516501645-1650.

BackgroundA convolutional neural network (CNN) is a deep learning (DL) model specialized for image processing, analysis, and classification.ObjectiveIn this study, we evaluated whether a CNN model using lateral cervical spine radiographs as input data can help assess fusion after anterior cervical discectomy and fusion (ACDF).Study DesignDiagnostic imaging study using DL.Patient SampleWe included 187 patients who underwent ACDF and fusion assessment with postoperative one-year computed tomography and neutral and dynamic lateral cervical spine radiographs.Outcome MeasuresThe performance of the CNN-based DL algorithm was evaluated in terms of accuracy and area under the curve.Materials And MethodsFusion or nonunion was confirmed by cervical spine computed tomography. Among the 187 patients, 69.5% (130 patients) were randomly selected as the training set, and the remaining 30.5% (57 patients) were assigned to the validation set to evaluate model performance. Radiographs of the cervical spine were used as input images to develop a CNN-based DL algorithm. The CNN algorithm used three radiographs (neutral, flexion, and extension) per patient and showed the diagnostic results as fusion (0) or nonunion (1) for each radiograph. By combining the results of the three radiographs, the final decision for a patient was determined to be fusion (fusion ≥2) or nonunion (fusion ≤1). By combining the results of the three radiographs, the final decision for a patient was determined as fusion (fusion ≥2) or nonunion (nonunion ≤1).ResultsThe CNN-based DL model demonstrated an accuracy of 89.5% and an area under the curve of 0.889 (95% confidence interval, 0.793-0.984).ConclusionThe CNN algorithm for fusion assessment after ACDF trained using lateral cervical radiographs showed a relatively high diagnostic accuracy of 89.5% and is expected to be a useful aid in detecting pseudarthrosis.Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.

19 keywords...

hide…